Best local AI models for AMD R9 M375

The largest models that fit fully

The 30 largest of the 56 models that fit; every smaller model in the catalog fits too. Best quant means the highest quality compression whose weights and 4k context both sit inside the memory.

Close, but only with CPU offload

These need more than the card holds at their smallest practical quant, so part of the model runs from system memory (figures assume 32 GB of it). They work, several times slower.

How to read this

The AMD Radeon R9 M375 is an older mobile graphics card equipped with 2 GB of DDR3 video memory. This dedicated memory size is the main limiting factor for running local artificial intelligence models. To run a model entirely on this hardware, the model files and active memory must fit within this 2 GB limit. If a model exceeds this capacity, your system must use alternative execution methods.

The quantization column indicates the compression level applied to each model. Quantization reduces the precision of model weights to save space. For example, the Allegro 2.8B model fits in 2 GB of video memory when using the Q4_K_M quantization. Smaller models like the SmolVLM 2B or Stable Diffusion 3 Medium can run at a higher quality Q6_K quantization while still using exactly 2 GB of video memory. TinyLlama 1.1B runs at a high quality Q8_0 quantization and uses only 1.4 GB of video memory.

When a model is too large for the 2 GB video memory, you can use CPU offload. This method splits the workload between your graphics card and your system RAM. We assume your computer has 32 GB of system RAM for these scenarios. For example, running the SmolLM3 3B model requires 2.2 GB of video memory at Q4_K_M quantization and needs an additional 4.2 GB of system RAM. Similarly, the Stable Diffusion XL model requires 4.1 GB at FP8 or optimized settings and needs 6.1 GB of system RAM.

Using CPU offload allows you to run larger models like MusicGen or SDXL Turbo on your system. However, offloading data to system RAM comes with a performance cost. DDR3 video memory is already slow, and transferring data to system RAM creates a bottleneck. This transfer process significantly reduces the generation speed compared to running a model entirely inside the 2 GB video memory.

You must also consider the active context window when running text models. The memory numbers listed here represent the model at its base state. Running a model with a long 4k context window requires additional memory for the active session data. This extra memory usage can easily push a model over the 2 GB limit, so you may need to use a smaller model or a lower quantization to maintain stable performance.